Publication

[Journal Papers]

1. Yuka Hashimoto, Fuyuta Komura, and Masahiro Ikeda, Hilbert C*-module for analyzing structured data, Matrix and Operator Equations, pp 633-659, 2023.
2. Yuka Hashimoto and Takashi Nodera, A preconditioning technique for Krylov subspace methods in RKHSs, J. Comput. Appl. Math., 415: 114490, 2022.
3. Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Fuyuta Komura, Takeshi Katsura, and Yoshinobu Kawahara, Reproducing kernel Hilbert C*-module and kernel mean embeddings, JMLR, 22, 267:1-56, 2021.
4. Yuka Hashimoto and Takashi Nodera, Krylov subspace methods for estimating operator-vector multiplications in Hilbert spaces, Japan J. Indust. Appl. Math, 38, pp781-803, 2021.
5. Yuka Hashimoto and Takashi Nodera, Inexact rational Krylov method for evolution equations, BIT Numer. Math., 61, pp473-502, 2021 (Correction to: Inexact rational Krylov method for evolution equations, BIT Numer. Math., 61, 1483-1487, 2021).
6. Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Yoichi Matsuo, and Yoshinobu Kawahara, Krylov subspace method for nonlinear dynamical systems with random noise, JMLR, 21, 172: 1-29, 2020.
7. Yuka Hashimoto and Takashi Nodera, Shift-invert Rational Krylov method for an operator φ-function of an unbounded linear operator, Japan J. Indust. Appl. Math, 36, pp421-433, 2019.
8. Yuka Hashimoto and Takashi Nodera, Double-shift-invert Arnoldi method for computing the matrix exponential, Japan J. Indust. Appl. Math, 35, pp727-738, 2018.
9. Yuka Hashimoto and Takashi Nodera, Shift-invert rational Krylov method for evolution equations, 18th Computational Techniques and Applications Conference, ANZIAM Journal, Vol. 58, pp. C149-C161, 2017.
10. Yuka Hashimoto and Takashi Nodera, Inexact shift-invert Arnoldi method for evolution equations, ANZIAM Journal, Vol. 58, pp. E1-E27, 2016.
11. Yuka Hashimoto and Takashi Nodera, Inexact shift-invert Arnoldi method for linear evolution equations (Japanese), IPSJ Journal, Vol. 57，No. 10, pp. 2250-2259, 2016.

[International Conferences]

1. Yuka Hashimoto, Masahiro Ikeda, and Hachem Kadri, C*-Algebraic Machine Learning ― Moving in a New Direction (Position Paper), accepted for ICML 2024.
2. Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, and Taiji Suzuki, Koopman-based generalization bound: New aspect for full-rank weights, ICLR 2024.
3. Yuka Hashimoto, Masahiro Ikeda, and Hachem Kadri, Deep learning with kernels through RKHM and the Perron-Frobenius operator, NeurIPS 2023.
4. Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, and Masahiro Ikeda, Deep Ridgelet transform: Voice with Koopman operator proves universality of formal deep networks, NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations.
5. Yuka Hashimoto, Masahiro Ikeda, and Hachem Kadri, Learning in RKHM: a C*-algebraic twist for kernel machines, AISTATS 2023.
6. Yuka Hashimoto, Zhao Wang, and Tomoko Matsui, C*-algebra net: a new approach generalizing neural network parameters to C*-algebra, ICML 2022. [code]
7. Isao Ishikawa, Keisuke Fujii, Masahiro Ikeda, Yuka Hashimoto, and Yoshinobu Kawahara, Metric on nonlinear dynamical systems with Koopman operators, NeurIPS 2018.